AI Tool Validates Over 100 New Exoplanets in TESS Data

RAVEN pipeline finds thousands of candidates, provides best estimate of planets around Sun-like stars

Apr. 1, 2026 at 4:18pm

Got story updates? Submit your updates here. ›

A team of exoplanet researchers used a new machine learning tool called RAVEN to analyze TESS transit data for over 2 million stars, validating 118 new planets and identifying over 2,000 high-quality planet candidates, nearly 1,000 of them entirely new. The results provide important insights into the prevalence of close-in exoplanets and the mysterious 'Neptune desert' region.

Why it matters

As powerful telescopes and surveys generate ever-increasing amounts of astronomical data, advanced AI and machine learning tools are becoming essential for efficiently processing and extracting meaningful insights. The RAVEN pipeline represents a significant advance in exoplanet detection and validation, helping to build a more detailed understanding of planetary populations and formation processes.

The details

The RAVEN (RAnking and Validation of ExoplaNets) pipeline was developed specifically to analyze TESS transit data, which is prone to false positives from eclipsing binary stars, stellar variability, and other astrophysical phenomena. By training machine learning models on a large dataset of simulated planets and other events, RAVEN can accurately distinguish true exoplanet signals. The pipeline handles the entire workflow, from initial detection to statistical validation.

  • The research paper was published in the Monthly Notices of the Royal Astronomical Society in April 2026.

The players

Marina Lafarga Magro

Postdoctoral Researcher at the University of Warwick and lead author of the study.

Andreas Hadjigeorghiou

Researcher at the University of Warwick who led the development of the RAVEN pipeline.

David Armstrong

Associate Professor at the University of Warwick and senior co-author of the study.

Kaiming Cui

Postdoctoral Researcher at the University of Warwick and first author of a companion study on the demographics of close-in TESS exoplanets.

RAVEN

A newly developed machine learning pipeline for vetting and validating exoplanet candidates from TESS data.

Got photos? Submit your photos here. ›

What they’re saying

“Using our newly developed RAVEN pipeline, we were able to validate 118 new planets, and over 2,000 high-quality planet candidates, nearly 1,000 of them entirely new. This represents one of the best characterised samples of close in planets and will help us identify the most promising systems for future study.”

— Marina Lafarga Magro, Postdoctoral Researcher, University of Warwick

“The challenge lies in identifying if the dimming is indeed caused by a planet in orbit around the star or by something else, like eclipsing binary stars, which is what RAVEN tries to answer. Its strength stems from our carefully created dataset of hundreds of thousands of realistically simulated planets and other astrophysical events that can masquerade as planets. We trained machine learning models to identify patterns in the data that can tell us the type of event we have detected, something that AI models excel at.”

— Andreas Hadjigeorghiou, Researcher, University of Warwick

“For the first time, we can put a precise number on just how empty this 'desert' is. These measurements show that TESS can now match, and in some cases surpass, Kepler for studying planetary populations.”

— Kaiming Cui, Postdoctoral Researcher, University of Warwick

What’s next

The researchers plan to continue refining the RAVEN pipeline and applying it to additional TESS data to further expand the catalog of validated exoplanets and better understand the demographics of planetary systems around Sun-like stars.

The takeaway

The RAVEN pipeline represents a significant advance in exoplanet detection and validation, leveraging machine learning to efficiently process large astronomical datasets and provide crucial insights into the prevalence and characteristics of close-in exoplanets. This work will help guide future exoplanet research and the search for potentially habitable worlds.